© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 60730
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pes
    -0.07
    纶
    -0.07
    alfa
    -0.07
    _aux
    -0.07
    osaic
    -0.07
    迹
    -0.07
    wares
    -0.07
    neb
    -0.07
    imb
    -0.06
    æĪijçļĦæĶ¶èĹı
    -0.06
    POSITIVE LOGITS
    被åĪĹ为
    0.07
    ebi
    0.07
    borg
    0.07
    人çĶŁ
    0.07
    交代
    0.06
    è¾ĵåħ¥çļĦ
    0.06
    女主è§Ĵ
    0.06
    anton
    0.06
    omotor
    0.06
    atee
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.